Files
mw-macbook-pro/scripts/vision-bridge.sh
T

33 lines
706 B
Bash
Executable File

#!/usr/bin/env bash
set -euo pipefail
# vision-bridge.sh: Bridge Peekaboo screenshots to Ollama Vision
# Usage: ./vision-bridge.sh "Describe this screen" [app_name]
PROMPT="${1:-Describe this image}"
APP="${2:-}"
RETINA="${3:-true}"
TMP_IMG=$(mktemp /tmp/openclaw-vision-XXXXXX.png)
cleanup() {
rm -f "$TMP_IMG"
}
trap cleanup EXIT
# Capture
PEEKABOO_ARGS=(image --path "$TMP_IMG")
if [ -n "$APP" ]; then
PEEKABOO_ARGS+=(--app "$APP")
fi
if [ "$RETINA" = "true" ]; then
PEEKABOO_ARGS+=(--retina)
fi
echo "[vision] Capturing screen..." >&2
peekaboo "${PEEKABOO_ARGS[@]}" >/dev/null
# Analyze
echo "[vision] Analyzing with llama3.2-vision..." >&2
ollama run llama3.2-vision "$PROMPT" "$TMP_IMG"